Collaborating Authors

Weaver, Lex

The Optimal Reward Baseline for Gradient-Based Reinforcement Learning Artificial Intelligence

There exist a number of reinforcement learning algorithms which learnby climbing the gradient of expected reward. Their long-runconvergence has been proved, even in partially observableenvironments with non-deterministic actions, and without the need fora system model. However, the variance of the gradient estimator hasbeen found to be a significant practical problem. Recent approacheshave discounted future rewards, introducing a bias-variance trade-offinto the gradient estimate. We incorporate a reward baseline into thelearning system, and show that it affects variance without introducingfurther bias. In particular, as we approach the zero-bias,high-variance parameterization, the optimal (or variance minimizing)constant reward baseline is equal to the long-term average expectedreward. Modified policy-gradient algorithms are presented, and anumber of experiments demonstrate their improvement over previous work.

TDLeaf(lambda): Combining Temporal Difference Learning with Game-Tree Search Artificial Intelligence

In this paper we present TDLeaf(lambda), a variation on the TD(lambda) algorithm that enables it to be used in conjunction with minimax search. We present some experiments in both chess and backgammon which demonstrate its utility and provide comparisons with TD(lambda) and another less radical variant, TD-directed(lambda). In particular, our chess program, ``KnightCap,'' used TDLeaf(lambda) to learn its evaluation function while playing on the Free Internet Chess Server (FICS, It improved from a 1650 rating to a 2100 rating in just 308 games. We discuss some of the reasons for this success and the relationship between our results and Tesauro's results in backgammon.